Mentoring system
Patent Information
- Application Number
- JP2025543523
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Priority Date
- 2023-08-28
- Filing Date
- 2024-08-27
- Publication Date
- 2025-03-06
Abstract
Description
Mentoring System
[0001] The present invention relates to a mentoring system.
[0002] It is common for someone with experience in a certain field to act as a mentor and provide consultation and advice to someone with less experience in that field.
[0003] However, since mentors are human, the content of their advice may change from day to day, or they may give advice that is inappropriate for the personality of the user receiving the advice.
[0004] In this regard, technologies have been proposed that select a trained model that suits the user's personality, have this trained model generate advice, and then provide the advice to the user in expressions that suit the user's personality (e.g., Patent Document 1, particularly Example 3), as well as technologies that quantify the user's characteristics and change the content of instruction based on these numerical values (e.g., Patent Document 2).
[0005] Furthermore, it has recently become possible to generate advice using so-called generative AI, which allows for more flexible advice tailored to the user's individuality.
[0006] However, a certain level of skill is required for the generation AI to output the desired information based on the input information.
[0007] Japanese Patent No. 6550603 Japanese Patent Laid-Open No. 2006-64880
[0008] The problem to be solved by the present invention is to provide a mentoring system that generates information for input to a generation AI suitable for mentoring without user intervention and mentors the user.
[0009] The present invention provides a mentoring system comprising: a prompt template database that stores prompt templates to be input to a generation AI; a mentor attribute database that stores mentor personality information for each mentor, which is text data that indicates the mentor's attributes and personality as a person; and a control unit that reads the template selected from the prompt template database, generates the prompt by reading and applying the mentor personality information of the mentor selected from the mentor attribute database to the read template, sends the generated prompt to a generation AI server that comprises the generation AI 21, receives output data output by the generation AI after processing the prompt, and sends it to a user terminal.
[0010] According to the present invention, it is possible to provide a mentoring system that generates information for input to a generation AI suitable for mentoring without user intervention and provides mentoring to a user.
[0011] 1 is a block diagram showing the configuration of a mentoring system of a first embodiment. 2 is a diagram showing the data configuration of a prompt template database. 3 is a diagram showing the data configuration of a mentor attribute database. 4 is a diagram showing the data configuration of a user data database. 5 is a flowchart showing a mentoring operation. 6 is a block diagram showing the configuration of a mentoring system of a second embodiment. 7 is a flowchart showing a trained model generation operation. 8 is a flowchart showing a teacher prompt generation and a learning processing operation of the generation AI. 9 is a flowchart showing the mentoring operation of a mentoring system of a fourth embodiment. 10 is a diagram showing an example of a rubric. 11 is a diagram showing an example of a prompt template including a request for suitable career suggestions. 12 is a block diagram showing the configuration of a mentoring system of a fifth embodiment. 13 is a flowchart showing the mentoring operation of the mentoring system of the fifth embodiment. 14 is a block diagram showing the configuration of a mentoring system of a sixth embodiment. 15 is a flowchart showing the mentoring operation of the mentoring system of the sixth embodiment. 16 is a block diagram showing the mentoring operation of the mentoring system of the sixth embodiment. 17 is a block diagram showing the configuration of a mentoring system of a ninth embodiment. 18 is a flowchart showing the mentor presentation operation of a mentoring system of the ninth embodiment.
[0012] A mentoring system according to an embodiment of the present invention will be described in detail below.
[0013] (Generated AI) This embodiment uses so-called generated AI, so this generated AI will be explained first.
[0014] In general, conventional trained models are structured by clearly separating explanatory variables and objective variables, and the structured data is used as training data for the model to learn. For example, when the model is a so-called neural network, explanatory variables are input, and a model that outputs a desired objective variable is selected, and this model is adopted as the trained model.
[0015] When a trained model generated in this way receives inputs that are somewhat similar to the explanatory variables of the training data, it outputs processing results that are somewhat similar to the objective variables of the training data. However, it cannot be expected to produce processing results that differ from the objective variables of the training data.
[0016] In contrast, if a model is trained using unstructured training data such as those described above, it becomes possible to obtain somewhat creative processing results.
[0017] For example, if a model is trained using hundreds of thousands to millions of question and answer combinations from a conventional online chat system with a human responder, the trained model will respond very smoothly. When this trained model is then "requested" to create something, it will output or generate a processing result that is somewhat creative. The text data indicating this "request" is called a prompt.
[0018] Trained models that produce somewhat creative processing results like this are now called generative AI. Generative AI can generate program code, images, videos, audio, and more. Generative AI that generates text data, such as ChatGPT, is becoming increasingly popular.
[0019] ChatGPT is already in commercial operation, and the vendor provides an API (Application Programming Interface), making it easy to use.
[0020] 1 is a block diagram showing the configuration of a mentoring system 1 according to a first embodiment. As shown in FIG. 1, the mentoring system 1 can be realized using a so-called server device or computer. The mentoring system 1 includes a control unit 11, a storage unit 12, an input / output unit 13, and a communication unit 14.
[0021] The control unit 11 includes a calculation device such as a CPU (central processing unit), etc. The control unit 11 sequentially reads out and executes the programs stored in the storage unit 12.
[0022] The storage unit 12 includes storage devices such as a memory, an SSD (Solid State Drive), a hard disk drive, etc. The storage unit 12 stores a prompt template DB 121 (a database is referred to as a DB), a mentor attribute DB 122, an API specification DB 123 for each generated AI, a user data DB 124, and an interface DB 125.
[0023] The API specification DB 123 for each generated AI stores the specifications of the API set for each generated AI 21 of the generated AI server 2.
[0024] The interface DB 125 stores the specifications of data to be displayed on the user terminal 4 .
[0025] The input / output unit 13 includes input / output devices such as a mouse, a keyboard, and a display.
[0026] The communication unit 14 includes a communication device that can connect to a public communication network such as the Internet 3. The mentoring system 1 is connected to the generation AI server 2 including the generation AI 21 and the user terminal 4 via the communication unit 14.
[0027] Fig. 2 is a diagram showing the data configuration of the prompt template DB 121. As shown in Fig. 2, the prompt template DB 121 stores a template ID, which is an identifier uniquely assigned to each template, a prompt purpose indicating the purpose for which the prompt is to be used, role setting information, which is information setting the role to be played by the generation AI 21, a mentor personality information FILLER indicating an area for storing information indicating the personality of the mentor, goal setting information, which indicates the goal to be described in the request content of the prompt, and flow setting information, which indicates the procedure for communication between the generation AI 21 and the user terminal and the procedure for information processing to be performed by the generation AI 21.
[0028] 3 is a diagram showing the data configuration of the mentor attribute DB 122. As shown in FIG. 3, the mentor attribute DB 122 stores a mentor ID, which is identification information uniquely assigned to each mentor, and mentor personality information, which is text data indicating the mentor's attributes and personality as a person. Here, mentors in the present invention include not only living people, but also deceased people, fictional characters appearing in movies, novels, etc., and objects of faith such as religious gods and leaders. Furthermore, mentors in the present invention also include people younger than the user.
[0029] Mentor personality information may include, for example, date of birth, self-introduction, likes and dislikes, position in family, people who have influenced them, position at work, favorite subjects, favorite songs, reasons for liking their favorite songs, how they spent their time after school in high school, things they have continued to do, and things they have explored so far, etc., which are text data that indicate the mentor's attributes and personality as a person or what kind of person the mentor is.
[0030] Fig. 4 is a diagram showing the data configuration of the user data DB 124. As shown in Fig. 4, the user data DB 124 stores a user ID, which is an identifier uniquely assigned to a user, user individuality information, which is text data indicating the user's attributes and individuality as a person, and question IDs, which are identifiers uniquely assigned to each question in a separately provided question DB that stores questions, and user answer information, which is text data indicating the user's answer to each question.
[0031] User personality information includes, for example, gender, year of school, desired university, desired major, field of greatest interest, experience living abroad, language qualifications acquired, sports experience, music experience, awards won in contests, favorite books or movies, reasons for liking them, and what the user wants to contribute to society in the future, and other text data that indicates the user's attributes and personality as a person or what the user is like.
[0032] The questions stored in the question DB include text data, are designed to allow users' attributes and personalities to be expressed, and are not limited to one or a few answers. Examples of such questions include the questions described in paragraphs
[0029] to
[0038] of Japanese Patent No. 7320809, which is a patent application filed by the applicant.
[0033] 5 is a flowchart showing the mentoring operation performed by the control unit 11 of the mentoring system 1. As shown in Fig. 5, in step S1, the user terminal 4 transmits to the mentoring system 1 a mentoring request indicating that the user is requesting various consultations from a mentor.
[0034] In step S2, the control unit 11 executes a mentor presentation process, which is a process of sending a list of mentors who will provide mentoring to the user terminal. Specifically, the control unit 11 reads all or part of the mentor IDs and mentor personality information from the mentor attribute DB 122, generates data that lists the mentor IDs and mentor personality information in a viewable manner on the user terminal 4, and sends the data to the user terminal 4.
[0035] In step S3, the user terminal 4 transmits the mentor ID of the mentor selected by the user to the mentoring system 1.
[0036] In step S4 , the control unit 11 reads the mentor individuality information of the corresponding mentor ID from the mentor attribute DB 122 based on the mentor ID received from the user terminal 4 .
[0037] In step S5, the control unit 11 generates a prompt. Specifically, the control unit 11 first reads the template ID and prompt purpose from the prompt template DB 121 and transmits them to the user terminal 4 in a viewable manner. Next, the control unit 11 reads a template from the prompt template DB 121 based on the prompt ID corresponding to the prompt purpose selected by the user from the user terminal 4. The control unit 11 then sets the mentor personality information in a mentor personality information FILLER to generate a prompt and stores it in the memory of the storage unit 12.
[0038] In step S6, the control unit 11 reads the API specifications of the generated AI 21 to be used from the generated AI-specific API specification DB 123, and modifies the prompt in the memory as necessary based on the use of this API.
[0039] In step S7, the control unit 11 reads the prompt from memory and sends it to the generation AI server 2.
[0040] In step S8, the generation AI server 2 receives the prompt from the mentoring system 1, processes the received prompt appropriately, and then inputs it to the generation AI 21, causing the generation AI 21 to start processing.
[0041] In step S9, the generation AI server 2 generates a response sentence that is the result of processing based on the prompt and sends it to the mentoring system 1.
[0042] In step S10 , the control unit 11 transmits the received response sentence to the user terminal 4 .
[0043] In step S11 , if the received response text includes an instruction to input additional information, the user terminal 4 inputs the additional information and transmits it to the mentoring system 1 .
[0044] The mentoring system 1 mediates the exchange of data between the generation AI server 2 and the user terminal 4 as many times as necessary, as in the above-mentioned steps S9 → S10 → S11 → S10 → S9.
[0045] In step S12, the generation AI 21 generates an answer sentence, and the generation AI server 2 sends this answer sentence to the mentoring system 1.
[0046] In step S13 , the control unit 11 transmits the response text to the user terminal 4 .
[0047] In step S14, the user terminal 4 receives the answer sentence, displays it on a display unit such as a display that the user terminal 4 has, and ends the process.
[0048] As described above, the mentoring system 1 of this embodiment comprises a prompt template DB 121 that stores prompt templates to be input to the generation AI 21, a mentor attribute DB 122 that stores mentor personality information for each mentor, which is text data that indicates the mentor's attributes and personality as a person, and a control unit that reads a template selected from the prompt template DB 121, generates a prompt by reading and applying the mentor personality information of the mentor selected from the mentor attribute DB 122 to the read template, sends the generated prompt to the generation AI server 2 that comprises the generation AI 21, receives the output data that the generation AI 21 processes and outputs the prompt, and sends it to the user terminal 4.
[0049] Therefore, according to the first embodiment of the present invention, a prompt, which is information for input to the generation AI suitable for mentoring, can be generated without user intervention, the prompt can be input to the generation AI 21, and the output data output by the generation AI 21 after processing the prompt can be sent to the user terminal 4, thereby providing a mentoring system 1 that mentors the user.
[0050] Second Embodiment In the mentoring system 1 of the first embodiment, mentor personality information is stored in advance in the mentor attribute DB 122. In contrast, the mentoring system 1 of the present embodiment creates training data including mentor personality information as an explanatory variable and information specifying the mentor, such as a mentor ID, as a target variable, causes the external AI 51, which is a model of the external AI server 5, to learn this training data to generate a trained model, inputs user personality information and user response information into this trained model, and outputs information specifying a mentor suitable for the user, thereby eliminating the need for the user to select a mentor.
[0051] Fig. 6 is a block diagram showing the configuration of a mentoring system 1 according to the second embodiment. As shown in Fig. 6, the mentoring system 1 can be realized using a so-called server device or computer. The mentoring system 1 includes a control unit 11, a storage unit 12, an input / output unit 13, and a communication unit 14.
[0052] The control unit 11 includes a calculation device such as a CPU, etc. The control unit 11 sequentially reads out and executes the programs stored in the storage unit 12.
[0053] The storage unit 12 includes a storage device such as a memory, an SSD, a hard disk drive, etc. The storage unit 12 stores a prompt template DB 121, a mentor attribute DB 122, an API specification DB 123 for each generated AI, a user data DB 124, and an interface DB 125.
[0054] The API specification DB 123 for each generated AI stores the specifications of the API set for each generated AI 21 of the generated AI server 2.
[0055] The interface DB 125 stores the specifications of data to be displayed on the user terminal 4 .
[0056] The input / output unit 13 includes input / output devices such as a mouse, a keyboard, and a display.
[0057] The communication unit 14 includes a communication device that can connect to a public communication network such as the Internet 3. The mentoring system 1 is connected to a generation AI server 2 that includes a generation AI 21, an external AI server 5 that includes an external AI 51, and a user terminal 4 via the communication unit 14.
[0058] The data structures of the prompt template DB121, mentor attribute DB122, API specification DB123 for each generated AI, user data DB124, and interface DB125 in this embodiment are the same as the data structures of the prompt template DB121, mentor attribute DB122, API specification DB123 for each generated AI, user data DB124, and interface DB125 in the first embodiment.
[0059] 7 is a flowchart showing the trained model generation operation performed by the control unit 11 of the mentoring system 1. As shown in Fig. 7, in step S101, the control unit 11 reads thousands to tens of thousands of data sets at once, each data set combining information identifying a mentor and mentor personality information.
[0060] In step S102, the control unit 11 creates teacher data including mentor personality information as an explanatory variable and information for identifying the mentor, such as a mentor ID, as a target variable.
[0061] In step S103, the control unit 11 transmits the created teacher data to the external AI server 5.
[0062] In step S104, the external AI server 5 receives the training data.
[0063] In step S105, the external AI server 5 trains a model using the received training data, generates a trained model that outputs information identifying a mentor when user personality information and user response information are input, and ends the processing.
[0064] Next, the mentoring operation of this embodiment will be described. In the mentoring operation performed by the control unit 11 of the mentoring system 1 of this embodiment, step S2 of the mentoring operation performed by the control unit 11 of the mentoring system 1 of the first embodiment is as follows: "In step S2, the control unit 11 executes a mentor presentation process, which is a process of sending a list of mentors who will provide mentoring to the user terminal. Specifically, the control unit 11 reads user personality information and user answer information from the user data DB 124 based on the user ID entered by the user who requested mentoring at the time of login, sends this to the external AI server 5 for processing by the external AI 51, generates data that lists the mentor list output by the external AI 51 as a processing result in a viewable state on the user terminal 4, and sends this data to the user terminal 4." The processing of steps other than those described above is the same as the mentoring operation of the first embodiment.
[0065] As described above, the mentoring system 1 of this embodiment includes a prompt template DB 121 that stores prompt templates to be input to the generation AI 21, a mentor attribute DB 122 that stores mentor personality information, which is text data indicating the mentor's attributes and personality as a person, for each mentor, a user data DB 124 that stores user personality information and user answer information, which are text data indicating the user's attributes and personality as a person, and a user data DB 125 that reads out a template selected from the prompt template DB 121 and generates information to identify the mentor when the user personality information and user answer information are input in advance. The system comprises a control unit that inputs user personality information and user response information of the user to be mentored read from the user data DB124 into a trained model that has been trained to output the user personality information and user response information of the user to be mentored read from the user data DB124, transmits information identifying the mentor output by the trained model to the user terminal 4, reads the mentor personality information of the selected mentor received from the user terminal 4 from the mentor attribute DB122 and applies it to the read template to generate a prompt, transmits the generated prompt to a generation AI server 2 that has a generation AI21, receives the output data that the generation AI21 processes and outputs the prompt, and transmits it to the user terminal 4.
[0066] Therefore, according to the second embodiment of the present invention, by outputting information identifying a mentor suitable for the user to a trained model as external AI 51, the user can be spared the trouble of selecting a mentor, and a prompt, which is information for inputting the generation AI suitable for mentoring, can be generated without user intervention, and this prompt can be input to the generation AI 21, and the output data output by the generation AI 21 after processing the prompt can be sent to the user terminal 4, thereby providing a mentoring system 1 that mentors the user.
[0067] (Third embodiment) In the mentoring system 1 of the first embodiment, mentor personality information is stored in advance in the mentor attribute DB 122. In contrast, the mentoring system 1 of this embodiment creates a teacher prompt including mentor personality information and information identifying the mentor, has the generation AI 21 of the generation AI server 2 learn this teacher prompt, inputs user personality information and user response information to this generation AI 21, and outputs information identifying a mentor suitable for the user, thereby eliminating the need for the user to select a mentor.
[0068] The configuration of the mentoring system 1 of this embodiment is similar to the configuration of the mentoring system 1 of the second embodiment.
[0069] 8 is a flowchart showing the teacher prompt generation and learning processing operation of the generation AI 21 performed by the control unit 11 of the mentoring system 1. As shown in Fig. 8, in step S201, the control unit 11 reads thousands to tens of thousands of data sets at once, each data set combining information specifying a mentor and mentor personality information.
[0070] In step S202, the control unit 11 creates a teacher prompt including the loaded data set. This teacher prompt includes a request sentence requesting the generation AI 21 to learn the data set.
[0071] In step S203, the control unit 11 transmits the created teacher prompt to the generation AI server 2.
[0072] In step S204, the generation AI server 2 receives the teacher prompt.
[0073] In step S205, the generation AI server 2 inputs the received teacher prompt into the generation AI 21 for processing, and trains the generation AI 21 to output information identifying the mentor when user personality information is input, and then terminates the processing.
[0074] Next, the mentoring operation in this embodiment will be described. In the mentoring operation performed by the control unit 11 of the mentoring system 1 of this embodiment, step S2 of the mentoring operation performed by the control unit 11 of the mentoring system 1 of the first embodiment is as follows: "In step S2, the control unit 11 executes a mentor presentation process, which is a process of sending a list of mentors who will provide mentoring to the user terminal. Specifically, the control unit 11 reads user personality information and user answer information from the user data DB 124 based on the user ID entered by the user who requested mentoring at the time of login, sends this to the generation AI server 2 for processing by the generation AI 21, generates data that lists the mentor list output by the generation AI 21 as a processing result in a viewable state on the user terminal 4, and sends this data to the user terminal 4."
[0075] The processing of steps other than those described above is the same as the mentoring operation of the first embodiment.
[0076] As described above, the mentoring system 1 of this embodiment includes a prompt template DB 121 that stores prompt templates to be input to the generation AI 21, a mentor attribute DB 122 that stores mentor personality information, which is text data indicating the mentor's attributes and personality as a person, for each mentor, a user data DB 124 that stores user personality information and user answer information, which are text data indicating the user's attributes and personality as a person, and a user data DB 125 that reads out a template selected from the prompt template DB 121 and generates information to identify the mentor when the user personality information and user answer information are input in advance. The system comprises a control unit that inputs user personality information and user response information of the user to be mentored read from the user data DB 124 into the generation AI 21 that has been trained to output the user personality information and user response information of the user to be mentored read from the user data DB 124, sends information identifying the mentor output by the generation AI 21 to the user terminal 4, reads the mentor personality information of the selected mentor received from the user terminal 4 from the mentor attribute DB 122 and applies it to the read template to generate a prompt, sends the generated prompt to the generation AI server 2 that has the generation AI 21, receives the output data that the generation AI 21 processes and outputs the prompt, and sends it to the user terminal 4.
[0077] Therefore, according to the third embodiment of the present invention, by having the generation AI 21 output information that identifies a mentor suitable for the user, the user can further reduce the effort required to select a mentor, and a mentoring system 1 can be provided that mentors the user by generating a prompt, which is information for input to the generation AI that is suitable for mentoring, without user intervention, inputting this prompt into the generation AI 21, and sending the output data generated by the generation AI 21 processing the prompt to the user terminal 4.
[0078] (Fourth Embodiment) In the mentoring systems 1 of the first to third embodiments, the content of mentoring is limited to advice. In contrast, the mentoring system 1 of this embodiment generates a rubric, which is an evaluation standard for evaluating a user's answers, and a prompt including a request to suggest a suitable occupation for the user, and sends the rubric to the generation AI server 2 for processing by the generation AI 21. Information regarding the suitable occupation for the user, which is the processing result of the generation AI 21, is sent to the user terminal 4. The rubric is stored in a rubric storage unit provided in the storage unit 12.
[0079] The configuration of the mentoring system 1 of this embodiment is similar to the configuration of the mentoring system 1 of the first embodiment.
[0080] 9 is a flowchart showing the mentoring operation performed by the control unit 11 of the mentoring system 1 of the fourth embodiment. As shown in Fig. 9, in step S301, the user terminal 4 transmits a career consultation request to the mentoring system 1, indicating that the user terminal 4 requests a mentor to consult about a career.
[0081] In step S302, the control unit 11 executes a mentor presentation process, which is a process of sending a list of mentors who will provide mentoring to the user terminal. Specifically, the control unit 11 reads all or part of the mentor IDs and mentor personality information from the mentor attribute DB 122, generates data that lists the mentor IDs and mentor personality information in a viewable manner on the user terminal 4, and sends the data to the user terminal 4.
[0082] In step S303, the user terminal 4 transmits the mentor ID of the mentor selected by the user to the mentoring system 1.
[0083] In step S304, the control unit 11 reads the mentor individuality information of the corresponding mentor ID from the mentor attribute DB 122 based on the mentor ID received from the user terminal 4.
[0084] In step S305, the control unit 11 reads out the rubric from the rubric storage unit.
[0085] In step S306, the control unit 11 generates a prompt. Specifically, the control unit 11 first reads the template ID and prompt purpose from the prompt template DB 121 and transmits them to the user terminal 4 in a viewable format. Next, the control unit 11 reads a template from the prompt template DB 121 based on the prompt ID corresponding to the prompt purpose selected by the user from the user terminal 4. Then, the control unit 11 reads the mentor personality information of the selected mentor from the mentor attribute DB 122. Furthermore, the control unit 11 reads a rubric from the rubric storage unit.
[0086] The control unit 11 sets the read mentor personality information in the mentor personality information FILLER of the template, and then adds the read rubric to the template.
[0087] The control unit 11 generates a prompt for suggesting suitable careers by adding to the template a request to display instructions on the user terminal 4 prompting the user to input information, to evaluate additional input answers entered by the user from the user terminal 4 using a rubric, and to suggest suitable careers for the user based on the obtained evaluation and additional answers.
[0088] In step S307, the control unit 11 reads the API specifications of the generation AI 21 to be used from the generation AI-specific API specification DB 123. Based on this API specification, the control unit 11 modifies the suitable career suggestion prompt in memory as necessary, and generates a suitable career suggestion prompt to be sent.
[0089] In step S308, the control unit 11 reads the prompt for sending suitable job suggestions from the memory and sends it to the generation AI server 2 equipped with the generation AI 21.
[0090] In step S309, the generation AI server 2 receives the prompt from the mentoring system 1, processes the received prompt appropriately, and then inputs it to the generation AI 21, causing the generation AI 21 to start processing.
[0091] In step S310, the generation AI server 2 generates a response sentence that is the result of processing by the generation AI 21 based on the prompt for sending suitable career suggestions, and sends this response sentence to the mentoring system 1.
[0092] In step S311, the control unit 11 transmits the received response sentence to the user terminal 4.
[0093] In step S312, if the received response message includes an instruction to input additional information, the user terminal 4 inputs the additional information and transmits it to the mentoring system 1.
[0094] The mentoring system 1 mediates the exchange of data between the generation AI server 2 and the user terminal 4 as many times as necessary, as in the above-mentioned steps S310 → S311 → S312 → S311 → S310.
[0095] In step S313, the generation AI 21 generates an answer sentence, and the generation AI server 2 sends this answer sentence to the mentoring system 1.
[0096] In step S314, the control unit 11 transmits the response sentence to the user terminal 4.
[0097] In step S315, the user terminal 4 receives the reply text, displays it on a display unit such as a display that the user terminal 4 has, and ends the process.
[0098] FIG. 10 is a diagram showing an example of a rubric. As shown in FIG. 10, the rubric includes, for each index, which is an evaluation perspective, evaluation criteria for evaluating a user-written text, points that convert the evaluation results into numerical values corresponding to the evaluation results of the user-written text evaluated according to these evaluation criteria, and the meanings indicated by the numerical values of the points. Each index includes an evaluation perspective, such as "insight," and evaluation criteria that represent the qualitative evaluation criteria for this index using text data. Approximately 5 to 20 indexes can be selected as appropriate.
[0099] 11 is a diagram showing an example of a prompt template including a request for suitable job suggestions. As shown in FIG. 11, the prompt template including a request for suitable job suggestions has, in the goal setting information, a statement that the goal is to suggest suitable jobs, and in the flow setting information, a request to the user to input additional information and a request for suitable job suggestions based on the input additional information are written in text data.
[0100] As described above, the mentoring system 1 of this embodiment comprises a prompt template DB 121 that stores a template ID and a prompt purpose for each prompt template to be input to the generation AI 21, a mentor attribute DB 122 that stores, for each mentor, mentor personality information, which is text data indicating the attributes and personality of the mentor as a person, a rubric storage unit that stores, for each indicator that is an evaluation viewpoint, evaluation criteria for evaluating a sentence written by a user and points that convert the evaluation result into a numerical value corresponding to the evaluation result obtained by evaluating the sentence written by the user based on the evaluation criteria, and a rubric storage unit that reads out the template ID and prompt purpose from the prompt template DB 121 and transmits them to the user terminal 4 in a viewable manner, and reads out a template from the prompt template DB 121 based on the prompt ID corresponding to the prompt purpose selected by the user from the user terminal 4, and stores the mentor personality information of the selected mentor from the mentor attribute DB 122. a control unit that reads out the mentor personality information, reads out the rubric from the rubric memory unit, reads out the API specifications of the generation AI21 to be used from the generation AI-specific API specification DB123, adds the read out mentor personality information to the mentor personality information FILLER of the template, and further adds the read out rubric to the template, and further generates a sending prompt by adding to the template requests to display on the user terminal 4 instructions to prompt the user for input, to evaluate additional input answers input by the user from the user terminal 4 using the rubric, and to suggest a suitable occupation for the user based on the obtained evaluation and additional input answers, modifies the sending prompt in the memory based on the read out API specifications, sends the modified sending prompt to the generation AI server 2 that has the generation AI21, processes the sending prompt received by the generation AI21 and outputs the output data, which is received from the generation AI server 2 and sent to the user terminal 4.
[0101] Therefore, according to the fourth embodiment of the present invention, a sending prompt including information for input to the generation AI suitable for mentoring, a rubric which is an evaluation criterion for evaluating the user's answers, and a request to suggest an appropriate occupation that is suitable for the user, can be generated without user intervention, and the sending prompt can be input to the generation AI 21, and the output data output by the generation AI 21 after processing the sending prompt can be sent to the user terminal 4, thereby providing a mentoring system 1 that mentors the user.
[0102] Fifth Embodiment In the mentoring systems 1 of the first to fourth embodiments, the mentor attribute DB 122 stores text data indicating the attributes and personal characteristics of the mentor as the mentor personality information.
[0103] In contrast, in this embodiment, the mentor attribute DB 122 also stores video data as mentor personality information. The mentoring system 1 then transmits the video data from the mentor personality information of the designated mentor via the user terminal 4 to the video processing server 6, extracts audio and frame data from the video data, and converts the audio into text. Furthermore, the mentoring system 1 extracts a response set, which is a combination of a statement made by a person other than the mentor to the mentor and a statement made by the mentor in response to that statement, from the combination of frame data and text received from the video processing server 6, and generates a prompt including the response set.
[0104] Then, the mentoring system 1 sends a prompt including a response set to the generation AI server 2, has the video generation AI 22 process the prompt including the response set to generate an answer video, and sends the answer video received from the generation AI server 2 to the user terminal 4.
[0105] Fig. 12 is a block diagram showing the configuration of the mentoring system 1 of the fifth embodiment. As shown in Fig. 12, the mentoring system 1 has the same configuration as the mentoring system 1 of the first embodiment, but differs in that the mentor attribute DB 122 also stores video data as mentor individuality information.
[0106] If only video data is available as mentor individuality information, NULL is stored in the text storage location of the mentor attribute DB 122. Furthermore, the video portion of the video data is actually still image data (hereinafter, each still image data included in the video data will be referred to as frame data). Therefore, the mentor attribute DB 122 can also store still image data instead of video data as mentor individuality information.
[0107] Furthermore, in this embodiment, the generation AI server 2 includes a video generation AI 22. The video generation AI 22 learns using a preceding utterance set, which is a combination of text data and frame data of utterances made by a person (supporting actor) other than a certain person (hereinafter referred to as the leading actor) to the leading actor, as an explanatory variable, and a subsequent utterance set, which is a combination of text data and frame data of utterances made by the leading actor in response to the preceding utterance set, as a target variable, processes input text data, which is data to be processed, as utterances by a supporting actor, and outputs the leading actor's response to the data to be processed as frame data and text data.
[0108] The prompt specifies which of the characters appearing in the video data will be the main character.
[0109] The generation AI server 2 may further process the processed data using the video generation AI 22 to generate video data with audio and output it as processed data, or a separately provided video generation unit 51 may convert the text data of the processed data into audio data and combine the converted audio data with frame data of the processed data to generate video data and output it as processed data.
[0110] In this case, if the prompt contains video data, the generation AI server 2 first sends the video data of the prompt to the video processing server 6, has the video processing unit 61 generate text data and frame data from the video data, and receives the generated text data and frame data from the video processing server 6.
[0111] As the video processing unit 61, for example, several products such as the following have already been released: VEED.IO (https: / / www.veed.io / ja-JP / tools / video-to-text) Gglot (https: / / gglot.com / ja / mp4-to-text / ) DaVinci Resolve (https: / / www.blackmagicdesign.com / jp / products / davinciresolve / )
[0112] 13 is a flowchart showing the mentoring operation performed by the control unit 11 of the mentoring system 1 of this embodiment. As shown in Fig. 13, in step S1, the user terminal 4 transmits a mentoring request to the mentoring system 1, indicating that the user is requesting various consultations from a mentor.
[0113] In step S2, the control unit 11 executes a mentor presentation process, which is a process of sending a list of mentors who will provide mentoring to the user terminal. Specifically, the control unit 11 reads all or part of the mentor IDs and mentor personality information from the mentor attribute DB 122, generates data that lists the mentor IDs and mentor personality information in a viewable manner on the user terminal 4, and sends the data to the user terminal 4.
[0114] In step S3, the user terminal 4 transmits the mentor ID of the mentor selected by the user to the mentoring system 1.
[0115] In step S4 , the control unit 11 reads the mentor individuality information of the corresponding mentor ID from the mentor attribute DB 122 based on the mentor ID received from the user terminal 4 .
[0116] In step S4-1, the control unit 11 transmits the video data to the video processing server 6, causes the video processing unit 61 to generate text data and frame data from the video data, and receives the generated text data and frame data from the video processing server 6.
[0117] In step S4-2, the control unit 11 extracts a response set from the text data and frame data received from the video processing server 6, which is a combination of statements made by people other than the mentor who is a supporting actor to the mentor who is the main actor, and statements made by the mentor in response to these statements.
[0118] In step S5, the control unit 11 generates a prompt including a response set. Specifically, the control unit 11 first reads a template ID and a prompt purpose from the prompt template DB 121 and transmits them to the user terminal 4 in a viewable manner. Next, the control unit 11 reads a template from the prompt template DB 121 based on the prompt ID corresponding to the prompt purpose selected by the user from the user terminal 4. The control unit 11 then sets the mentor personality information in a mentor personality information FILLER to generate a prompt and stores it in the memory of the storage unit 12.
[0119] In step S6, the control unit 11 reads the API specifications of the generated AI 21 to be used from the generated AI-specific API specification DB 123, and modifies the prompt in the memory as necessary based on the use of this API.
[0120] In step S7, the control unit 11 reads the prompt from memory and sends it to the generation AI server 2.
[0121] In step S8, the generation AI server 2 receives a prompt from the mentoring system 1, processes the received prompt appropriately, and then inputs it into the video generation AI 22, causing the video generation AI 22 to start processing.
[0122] In step S9, the generation AI server 2 generates a response sentence / video as a result of processing based on the prompt and sends it to the mentoring system 1.
[0123] In step S10 , the control unit 11 transmits the received response text and video to the user terminal 4 .
[0124] In step S11 , if the user terminal 4 is instructed to add additional information to the received response text / video, the user terminal 4 makes the additional information and transmits it to the mentoring system 1 .
[0125] The mentoring system 1 mediates the exchange of data between the generation AI server 2 and the user terminal 4 as many times as necessary, as in the above-mentioned steps S9 → S10 → S11 → S10 → S9.
[0126] In step S12, the video generation AI 22 generates an answer video, and the generation AI server 2 transmits this answer video to the mentoring system 1.
[0127] In step S13 , the control unit 11 transmits the answer video to the user terminal 4 .
[0128] In step S14, the user terminal 4 receives the answer video, displays it on a display unit such as a display that the user terminal 4 has, and ends the process.
[0129] As described above, the mentoring system 1 of this embodiment comprises a prompt template DB 121 that stores prompt templates to be input to the video generation AI 22, a mentor attribute DB 122 that stores mentor personality information for each mentor, including video data that indicates the mentor's attributes and personality as a person, and a control unit that reads out a template selected from the prompt template DB 121, generates a prompt by reading out the mentor personality information of the mentor selected from the mentor attribute DB 122 and applying it to the read out template, sends the generated prompt to a generation AI server 2 that has the video generation AI 22, the generation AI server 2 processes the prompt and causes the video generation AI 22 to generate an answer video, receives the answer video from the generation AI server 2 and sends it to the user terminal 4.
[0130] Therefore, according to the fifth embodiment of the present invention, a mentoring system 1 can be provided that mentors a user by generating a prompt, which is information for input to the generation AI suitable for mentoring, without user intervention, having the generation AI 21 input this prompt, and sending the output data generated by the generation AI 21 processing the prompt to the user terminal 4, and further having the effect of allowing the user to receive mentoring from a mentor through video.
[0131] Furthermore, according to the fifth embodiment of the present invention, there is an advantage that mentoring can be received through video from people who exist only as videos, such as in movies, or from fictional characters in movies.
[0132] (Sixth embodiment) In the fifth embodiment, the mentoring system 1 causes the video processing unit 61 of the external video processing server 6 to process the video data, and the mentoring system 1 transmits the processed data processed by the video processing unit 61 to the generation AI server 2, which outputs the answer video.
[0133] In contrast, in the mentoring system 1 of the sixth embodiment, the generation AI server 2 has the video processing unit 61 inside the generation AI server 2 process the video data in the video generation AI 22, and the generation AI server 2 has the video generation AI 22 process the processed data processed by the video processing unit 61 to output an answer video.
[0134] Fig. 14 is a block diagram showing the configuration of a mentoring system 1 according to the sixth embodiment. As shown in Fig. 14, the mentoring system 1 has the same configuration as the mentoring system 1 according to the fifth embodiment, but differs in that the generation AI server 2 also includes a video processing unit 61, eliminating the need for a video processing server 6. Since the only difference is the location of the video processing unit 61, further explanation will be omitted.
[0135] 15 is a flowchart showing the mentoring operation performed by the control unit 11 of the mentoring system 1 of this embodiment. As shown in Fig. 15, in step S1, the user terminal 4 transmits a mentoring request to the mentoring system 1, indicating that the user is requesting various consultations from a mentor.
[0136] In step S2, the control unit 11 executes a mentor presentation process, which is a process of sending a list of mentors who will provide mentoring to the user terminal. Specifically, the control unit 11 reads all or part of the mentor IDs and mentor personality information from the mentor attribute DB 122, generates data that lists the mentor IDs and mentor personality information in a viewable manner on the user terminal 4, and sends the data to the user terminal 4.
[0137] In step S3, the user terminal 4 transmits the mentor ID of the mentor selected by the user to the mentoring system 1.
[0138] In step S4 , the control unit 11 reads the mentor individuality information of the corresponding mentor ID from the mentor attribute DB 122 based on the mentor ID received from the user terminal 4 .
[0139] In step S4-4, the control unit 11 transmits the video data to the generation AI server 2 and instructs it to learn the transmitted video data.
[0140] In step 4-5, the generation AI server 2 inputs the video data received from the mentoring system 1 into the video processing unit 61.
[0141] In step 4-6, the video processing unit 61 generates text data and frame data from the video data, and the generation AI server 2 stores the text data and frame data generated by the video processing unit 61 in a memory area separately provided within the memory unit 12.
[0142] In step S4-7, the control unit 11 extracts a response set from the text data and frame data read from the above-mentioned memory area, which is a combination of statements made by people other than the mentor who is a supporting actor to the mentor who is the main actor and the mentor's responses to these statements, and has the video generation AI 22 learn using the response set, as in the fifth embodiment.
[0143] In step S5, the control unit 11 generates a prompt including a response set. Specifically, the control unit 11 first reads a template ID and a prompt purpose from the prompt template DB 121 and transmits them to the user terminal 4 in a viewable manner. Next, the control unit 11 reads a template from the prompt template DB 121 based on the prompt ID corresponding to the prompt purpose selected by the user from the user terminal 4. The control unit 11 then sets the mentor personality information in a mentor personality information FILLER to generate a prompt and stores it in the memory of the storage unit 12.
[0144] In step S6, the control unit 11 reads the API specifications of the generated AI 21 to be used from the generated AI-specific API specification DB 123, and modifies the prompt in the memory as necessary based on the use of this API.
[0145] In step S7, the control unit 11 reads the prompt from memory and sends it to the generation AI server 2.
[0146] In step S8, the generation AI server 2 receives a prompt from the mentoring system 1, processes the received prompt appropriately, and then inputs it into the video generation AI 22, causing the video generation AI 22 to start processing.
[0147] In step S9, the generation AI server 2 generates a response sentence / video as a result of processing based on the prompt and sends it to the mentoring system 1.
[0148] In step S10 , the control unit 11 transmits the received response text and video to the user terminal 4 .
[0149] In step S11 , if the user terminal 4 is instructed to add additional information to the received response text / video, the user terminal 4 makes the additional information and transmits it to the mentoring system 1 .
[0150] The mentoring system 1 mediates the exchange of data between the generation AI server 2 and the user terminal 4 as many times as necessary, as in the above-mentioned steps S9 → S10 → S11 → S10 → S9.
[0151] In step S12, the video generation AI 22 generates an answer video, and the generation AI server 2 transmits this answer video to the mentoring system 1.
[0152] In step S13 , the control unit 11 transmits the answer video to the user terminal 4 .
[0153] In step S14, the user terminal 4 receives the answer video, displays it on a display unit such as a display that the user terminal 4 has, and ends the process.
[0154] As described above, the mentoring system 1 of this embodiment comprises a prompt template DB 121 that stores prompt templates to be input to the video generation AI 22, a mentor attribute DB 122 that stores mentor personality information for each mentor, including video data that indicates the mentor's attributes and personality as a person, and a control unit that reads a template selected from the prompt template DB 121, generates a prompt by reading the mentor personality information of the mentor selected from the mentor attribute DB 122 and applying it to the read template, sends the generated prompt to a generation AI server 2 that has a video generation AI 22 and a video processing unit 61 that generates text data and frame data from the video data, the generation AI server 2 processes the prompt, causes the video processing unit 61 to process the received video data, and causes the video generation AI 22 to process the obtained text data and frame data to generate an answer video, and receives the answer video from the generation AI server 2 and sends it to the user terminal 4.
[0155] Therefore, according to the sixth embodiment of the present invention, there is an effect that the processing speed can be increased more than in the fifth embodiment.
[0156] (Seventh embodiment) In the fifth and sixth embodiments, the mentoring system 1 sends and receives response sentences written in text data between the user terminal 4, and exchanges information with the generation AI server 2 and the like based on this text data.
[0157] In contrast, in the mentoring system 1 of the seventh embodiment, the memory unit 12 converts voice data into text data and stores a text-to-voice conversion program that converts text data into voice data, and when the control unit 11 receives a request for voice mentoring from the user terminal 4, it reads the text-to-voice conversion program from the memory unit 12 and converts the user's voice data received from the user terminal 4 into text, thereby performing the operations of the fifth to sixth embodiments.
[0158] Therefore, according to the seventh embodiment of the present invention, there is an effect that mentoring can be received as if one were having a conversation with a mentor.
[0159] Eighth Embodiment In the fifth to seventh embodiments, the mentoring system 1 allows a person to receive mentoring from only one mentor.
[0160] In contrast, the mentoring system 1 in the eighth embodiment differs in that a user can specify two or more mentors via a user terminal 4 and present each mentor's response video to each other's mentors, thereby allowing the mentors to observe their discussions.
[0161] In the fifth to seventh embodiments, such usage is possible in the mentoring system 1 by storing mentor personality information of a plurality of mentors in the mentor attribute DB 122 and allowing selection of a plurality of mentors.
[0162] Therefore, according to the seventh embodiment of the present invention, it has the effect of enabling a user to participate in a discussion between two people from different eras, such as a discussion about electric cars between Nikola Tesla and Elon Musk, which would not be possible in reality.
[0163] Ninth Embodiment In the mentoring system 1 of the first to eighth embodiments, the control unit 11 executes a mentor presentation process, which is a process of sending a list of mentors who will provide mentoring to a user terminal. Specifically, the control unit 11 reads all or part of the mentor IDs and mentor personality information from the mentor attribute DB 122 (a database is referred to as a DB), generates data that lists the information in a viewable form on the user terminal 4, and sends the data to the user terminal 4.
[0164] In contrast, in this embodiment, in addition to the mentor IDs and mentor personality information stored in the mentor attribute DB 122, the control unit 11 inputs the user-specified field into the mentor recommendation AI 24, which is a trained model that has been trained to input the field specified by the user as an explanatory variable and output an expert in the field specified by the user as a target variable, and presents the output expert to the user as a recommended mentor. Specifically, the control unit 11 generates data that lists all or part of the mentor IDs and mentor personality information of the recommended mentors in a viewable state on the user terminal 4, and transmits the data to the user terminal 4.
[0165] Figure 16 is a block diagram showing the configuration of a mentoring system 1 of the ninth embodiment. As shown in Figure 16, the mentoring system 1 has the same configuration as the mentoring system 1 of the first embodiment, but differs in that the generation AI server 2 further includes a mentor recommendation AI 24, and the mentoring system 1 is connected to an expert information server 7 via the Internet 3. In this embodiment, the generation AI server 2 includes either or both of a video generation AI 22 and a sentence generation AI 23. Furthermore, when the generation AI server 2 includes the video generation AI 22, the mentoring system 1 is connected to a video processing server 6 via the Internet 3.
[0166] Here, the sentence generation AI 23 is a name changed to distinguish between the generation AI 21 and the video generation AI 22 of the first embodiment. The configuration of the video processing server 6 is the same as that of the video processing server 6 of the fifth embodiment. Therefore, only the mentor recommendation AI 24 and the expert information server 7 will be described.
[0167] The expert information server 7 includes an expert DB 71 that stores expert information such as the name of the expert, affiliation, research field, title and details of the paper or patent, tags related to the research content, etc. The expert information server 7 searches the expert DB 71 based on at least one of the expert information or other keywords, and outputs the expert information of the relevant expert.
[0168] An example of the expert information server 7 is "J-GLOBAL" (Japan Science and Technology Agency, https: / / jglobal.jst.go.jp / ).
[0169] The mentor recommendation AI 24 is a trained model that is trained to input a field specified by the user as an explanatory variable and output an expert in the field specified by the user as a target variable. The mentor recommendation AI 24 can use expert information stored in the expert DB 71 of the expert information server 7 as training data. An example of the learning operation is described below.
[0170] FIG. 17 is a flowchart showing the mentor presentation operation of the control unit 11 in this embodiment, which is performed instead of the "mentor presentation process S2" shown in the flowchart showing the mentoring operation performed by the control unit 11 of the mentoring system 1 of the first to eighth embodiments.
[0171] The mentoring operations performed by the control unit 11 other than the mentor presentation operation are the same as the mentoring operations performed by the control unit 11 of the mentoring systems 1 of the first to eighth embodiments, and therefore a description thereof will be omitted.
[0172] 17, in step S2-1 following step S1, the control unit 11 receives the field to which the mentor the user wishes to consult belongs, which was sent from the user terminal 4, as the field.
[0173] In step S2-2, the control unit 11 transmits an expert search instruction, which is an instruction to search for a designated field and experts such as researchers belonging to the designated field.
[0174] In step S2-3, the expert information server 7 searches the expert DB 71 based on the received specified field, and transmits the search results relating to the extracted experts to the mentoring system 1 as a response.
[0175] In step S2-4, the control unit 11 selects experts from the received information about experts based on predetermined filter conditions. The filter conditions can set selection criteria and the number of experts to be selected, such as "the top 30 experts with the most number of papers." The control unit 11 then transmits a provision instruction to the expert information server 7 to provide expert information about the selected experts.
[0176] In step S2-5, the control unit 11 searches the expert DB 71 based on the received information such as the name of the expert, and transmits the expert information of the selected expert, including information on research results such as papers and patents, as well as videos, if any, to the mentoring system 1.
[0177] In step S2-6, the control unit 11 transmits and presents the received expert information to the generation AI server 2, and instructs it to train a model using the transmitted expert information as training data.
[0178] In step S2-7, the generation AI server 2 trains the model so that information about the research field contained in the received expert information is used as an explanatory variable, and the name of the expert from the expert information in that field is output as the objective variable. A mentor recommendation AI 24 is generated as a trained model. The mentor recommendation AI 24 can perform additional learning if a new field is specified by the user. When the mentor recommendation AI 24 has been generated, the generation AI server 2 notifies the mentoring system 1 that generation of the mentor recommendation AI 24 has been completed.
[0179] In step S2-8, the control unit 11 sends the specified field to the generation AI server 2, inputs the specified field into the mentor recommendation AI 24, and instructs it to output expert information on a pre-specified number of experts, and transmits the output experts as recommended mentors to the mentoring system 1. The pre-specified number of people can also be narrowed down to, for example, three people.
[0180] In step S2-9, the generation AI server 2 inputs the received specified field into the mentor recommendation AI 24, outputs the expert information of the experts for a pre-specified number of people, and sends the output experts to the mentoring system 1 as recommended mentors.
[0181] In step S2-10, the control unit 11 sets the received mentor name as the mentor ID, stores the expert information as mentor personality information in the mentor attribute DB 122, generates data that lists the mentors in a viewable state on the user terminal 4, sends the data to the user terminal 4, and terminates the processing of the mentor presentation operation.
[0182] As described above, the mentoring system 1 of this embodiment comprises a mentor recommendation AI 24, which is a trained model that has been trained to input a field specified by the generation AI server 2 as an explanatory variable and output an expert in the specified field as a target variable, and the control unit 11 comprises an expert information acquisition unit that searches for expert information of experts in the specified field based on the specified field in the expert information server 7, which has an expert DB 71 that stores expert information, and transmits the search results, a mentor recommendation generation AI unit that instructs the generation AI server 2 to train a model using the expert information acquired by the expert information acquisition unit as training data and generate the mentor recommendation AI 24, which is a trained model, a recommended mentor acquisition unit that transmits the specified field received from the user terminal 4 to the generation AI server 2, inputs the specified field into the mentor recommendation AI 24 generated by the mentor recommendation generation AI unit, and outputs expert information of the expert, and a recommended mentor presentation unit that transmits the recommended mentor acquired by the recommended mentor acquisition unit to the user terminal 4.
[0183] Therefore, according to this embodiment, (1) by specifying a field, it is possible to know what kind of experts are available in that field and to easily designate an expert as a mentor, and (2) ordinary people, such as high school students, can ask questions to well-known experts as mentors, from whom they would not normally be able to easily ask questions or seek opinions, and thereby be exposed to the way experts think and feel.
[0184] 1 Mentoring system 2 Generation AI server 3 Internet 4 User terminal 5 External AI server 6 Video processing server 7 Expert information server 11 Control unit 12 Memory unit 13 Input / output unit 14 Communication unit 51 External AI 21 Generation AI 22 Video generation AI 23 Text generation AI 24 Mentor recommendation AI 61 Video processing unit 71 Expert DB 121 Prompt template DB 122 Mentor attribute DB 123 API specification DB for each generation AI 124 User data DB 125 Interface DB
Claims
1. A mentoring system comprising: a prompt template database that stores prompt templates to be input to a generation AI; a mentor attribute database that stores mentor personality information for each mentor, which is text data that indicates the attributes and personality of the mentor as a person; and a control unit that reads the template selected from the prompt template database, generates the prompt by reading and applying the mentor personality information of the mentor selected from the mentor attribute database to the read template, transmits the generated prompt to a generation AI server that comprises the generation AI, receives output data output by the generation AI after processing the prompt, and transmits the output data to a user terminal.
2. A mentoring system comprising: a prompt template database that stores prompt templates to be input to a generation AI; a mentor attribute database that stores mentor personality information for each mentor, which is text data indicating the mentor's attributes and personality as a person; a user data database that stores user personality information, which is text data indicating the user's attributes and personality as a person; and a control unit that reads out the template selected from the prompt template database, inputs the user personality information of the user to be mentored read from the user data database into a trained model that has been trained in advance to output information identifying the mentor when the user personality information is input, transmits the information identifying the mentor output by the trained model to a user terminal, generates the prompt by reading out the mentor personality information of the selected mentor received from the mentor attribute database and applying it to the read template, transmits the generated prompt to a generation AI server comprising the generation AI, and receives output data output by the generation AI after processing the prompt, and transmits it to the user terminal.
3. The mentoring system of claim 2, wherein the user individual information includes user answer information.
4. A mentoring system comprising: a prompt template database storing prompt templates to be input to a generation AI; a mentor attribute database storing mentor personality information for each mentor, which is text data indicating the mentor's attributes and personality as a person; a user data database storing user personality information, which is text data indicating the user's attributes and personality as a person; and a control unit which reads the template selected from the prompt template database, inputs the user personality information of the user to be mentored read from the user data database into the generation AI, which has been trained to output information identifying the mentor when the user personality information is input, transmits the information identifying the mentor output by the generation AI to a user terminal, generates the prompt by reading the mentor personality information of the selected mentor received from the mentor attribute database and applying it to the read template, transmits the generated prompt to a generation AI server comprising the generation AI, and receives output data output by the generation AI after processing the prompt, and transmits it to the user terminal.
5. The mentoring system of claim 4, wherein the user individual information includes user answer information.
6. A prompt template database that stores a template ID and a prompt purpose for each prompt template to be input to the generation AI; a mentor attribute database that stores, for each mentor, mentor personality information which is text data indicating the attributes and personality of the mentor as a person; a rubric storage unit that stores, for each indicator that is an evaluation perspective, a rubric including evaluation criteria for evaluating a text written by a user and points that convert the evaluation result into a numerical value corresponding to the evaluation result obtained by evaluating the text written by the user based on the evaluation criteria; and a method for reading out the template ID and prompt purpose from the prompt template database and transmitting them to a user terminal in a viewable manner, reading out the template from the prompt template database based on the prompt ID corresponding to the prompt purpose selected by the user from the user terminal, reading out the mentor personality information of the selected mentor from the mentor attribute database, and reading out the rubric from the rubric storage unit; A mentoring system comprising: a control unit that generates a sending prompt by adding the read-out mentor personality information and the read-out rubric to the template, and further adding requests to the template to display instructions on the user terminal to prompt the user for input, to evaluate additional input answers input by the user from the user terminal using the rubric, and to suggest a suitable career for the user based on the obtained evaluation and the additional input answers; sending the generated sending prompt to a generation AI server comprising the generation AI; and receiving output data generated by processing the prompt received by the generation AI from the generation AI server and sending it to the user terminal.
7. A mentoring system comprising: a prompt template database storing prompt templates to be input to a video generation AI; a mentor attribute database storing mentor personality information for each mentor, which is video data indicating the attributes and individual personality of the mentor; and a control unit which reads out the template selected from the prompt template database, generates the prompt by reading out the mentor personality information of the mentor selected from the mentor attribute database to the read out template and applying it, transmits the generated prompt to a generation AI server comprising the video generation AI, receives the answer video output by the video generation AI after processing the prompt, and transmits it to a user terminal.
8. A mentoring system comprising: a prompt template database storing prompt templates to be input to a video generation AI; a mentor attribute database storing mentor personality information for each mentor, which is video data indicating the attributes and individual personality of the mentor; and a control unit which reads out the template selected from the prompt template database, generates the prompt by reading out the mentor personality information of a plurality of mentors selected from the mentor attribute database to the read out template and applying it, transmits the generated prompt to a generation AI server comprising the video generation AI, receives answer videos output by the video generation AI after processing the prompt, and transmits the answer videos to a user terminal.
9. The mentoring system described in any one of claims 1 to 8, wherein the generation AI server comprises a mentor recommendation AI which is a trained model trained to input a specified field as an explanatory variable and output an expert in the specified field as a target variable, and the control unit comprises: an expert information acquisition unit which causes an expert information server having an expert database for storing expert information to search for expert information of experts in the specified field based on the specified field and transmit the search result; a mentor recommendation generation AI unit which instructs the generation AI server to train a model using the expert information acquired by the expert information acquisition unit as teaching data to generate a mentor recommendation AI which is a trained model; a recommended mentor acquisition unit which transmits the specified field received from a user terminal to the generation AI server and instructs the generation AI server to input the specified field into the mentor recommendation AI generated by the mentor recommendation generation AI unit and output expert information of an expert as a recommended mentor; and a recommended mentor presentation unit which transmits the recommended mentor acquired by the recommended mentor acquisition unit to the user terminal.